7T fMRI reveals feasibility of covert visual attention-based brain-computer interfacing with signals obtained solely from cortical grey matter accessible by subdural surface electrodes

Abstract

Objective: There is a growing interest in brain-computer interfaces (BCI) based on invasive technologies. fMRI is exceptionally suited for selecting implant sites since BOLD signals has been shown to correlate well spatially with electric potentials recorded from the brain surface. Previous studies show that it is possible to decode covertly directed visuospatial attention using fMRI. In the present study we increase the relevance of the fMRI analysis for surface-electrodes by only allowing voxels at the surface of the brain.

Methods: We classify visuospatial attention directed to four different directions (left, right, up and down) using a support vector machine while enforcing several spatial restrictions on the voxels available for the classifier. All the spatial restrictions applied are based on how accessible the brain areas are for implanted surface electrodes.

Results: The results show that fMRI signals from only the surface of the brain are sufficient for a good classification. Data also show that the topographical pattern is quite variable across subjects.

Conclusions: A good control of BCI systems based on signals from surface electrodes can be achieved using visuospatial attention. Due to the large spatial variations in brain topography, individual mapping with fMRI to locate the optimal electrode implant sites is essential.

Significance: Visuospatial attention promises to be an effective target for implanted BCI systems.

Keywords: ECoG; Support vector machine; Surface analysis; fMRI.